ClawHub
Back to skill

Security audit

Google Search Console

Security checks across malware telemetry and agentic risk

Overview

This skill is a read-only Google Search Console helper, but its OAuth setup prints sensitive tokens that users must handle carefully.

Install only if you are comfortable granting read-only access to your Search Console properties. Run the auth helper in a private local terminal, do not paste its output into shared logs or chats, store the client secret and refresh token in a protected secret store or private env file, and revoke the Google OAuth token if it is exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script prints the OAuth client ID, client secret, and refresh token directly to stdout. In many environments stdout is captured by terminal scrollback, shell history helpers, CI logs, IDE consoles, or session recording tools, which can expose long-lived credentials to unintended parties.

Credential Access

High
Category
Privilege Escalation
Content
print()
    print("=" * 60)
    print("SUCCESS! Add these to your .env file:")
    print("=" * 60)
    print()
    print(f"GOOGLE_CLIENT_ID={client_id}")
Confidence
95% confidence
Finding
.env

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.